2.4k citations · 3.7k across the 27 of their papers we have counts for
27 papers
VCSUM: A Versatile Chinese Meeting Summarization Dataset
Han Wu, Mingjie Zhan, Haochen Tan +3
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting s…
Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Framework
Ruijia Wu, Yuhang Wang, Huafeng Shi +3
Denoising diffusion models have shown remarkable potential in various generation tasks. The open-source large-scale text-to-image model, Stable Diffusion, becomes prevalent as it c…
Improving Robust Fairness via Balance Adversarial Training
Chunyu Sun, Chenye Xu, Chengyuan Yao +5
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the…
Universal Backdoor Attacks Detection via Adaptive Adversarial Probe
Yuhang Wang, Huafeng Shi, Rui Min +5
Extensive evidence has demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks, which motivates the development of backdoor attacks detection. Most detecti…
DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection
Gang Li, Xiang Li, Yujie Wang +3
The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., a…
Learning Locality and Isotropy in Dialogue Modeling
Han Wu, Haochen Tan, Mingjie Zhan +4
Existing dialogue modeling methods have achieved promising performance on various dialogue tasks with the aid of Transformer and the large-scale pre-trained language models. Howeve…